用jsoup解析HTML网页中的PHP数据


Parsing PHP data from HTML webpage with jsoup

我不完全确定该如何表达这个问题或给它起个标题,所以就这样吧。我正在使用jsoup来解析一个网页(http://champion.gg/statistics/),我正试图使用此代码从他们的表中抓取统计数据。

public void connect(String url) {
    try {
        Document doc = Jsoup.connect(url).userAgent("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.152 Safari/537.36").get();
        System.out.println(doc.toString());
        Element table = doc.select("table[class=table table-striped]").first();
        Element tbody = table.select("tbody").first();
        Iterator<Element> rows = tbody.select("tr").iterator();
        rows.forEachRemaining(row -> {
            System.out.println(row.toString());
        });
    } catch(IOException exception) {
        if(Settings.DEBUG) {
            Program.LOGGER.log(Level.SEVERE, "There was an error reading the document with the supplied URL!", exception);
        }
        Program.alert("Error loading webpage!");
    }
}

,它产生这个结果

<tr ng-repeat="champion in filteredChampions = (championData | startsWith:search.title | filter:roleSort | orderBy:[order+sortExpression.sortBy,order+sortExpression.lastSortBy])"> 
 <td class="rank">{{indexNumber($index, filteredChampions.length)}}</td> 
 <td ng-class="{'selected-column':determineSelected('title')}"> <a href="/champion/{{champion.key}}/{{champion.role}}"> 
  <div class="tsm-tooltip tsm-angular-champion-tt" data-type="champions" data-name="{{champion.key}}" data-id="{{matchupData}}"> 
   <div class="matchup-champion {{champion.key}}"></div> 
   <span class="stat-champ-title">{{champion.title}}</span> 
  </div> </a> </td> 
 <td class="stats-role-title" ng-class="{'selected-column':determineSelected('role')}">{{champion.role}}</td> 
 <td ng-class="{'selected-column':determineSelected('winPercent')}"> <span ng-class="{'top-half': (champion.general.winPercent >= 50), 'bottom-half': (champion.general.winPercent < 50)}">{{champion.general.winPercent}}%</span> </td> 
 <td ng-class="{'selected-column':determineSelected('playPercent')}">{{champion.general.playPercent}}%</td> 
 <td ng-class="{'selected-column':determineSelected('banRate')}">{{champion.general.banRate}}%</td> 
 <td ng-class="{'selected-column':determineSelected('experience')}">{{champion.general.experience}}</td> 
 <td ng-class="{'selected-column':determineSelected('kills')}">{{champion.general.kills}}</td> 
 <td ng-class="{'selected-column':determineSelected('deaths')}">{{champion.general.deaths}}</td> 
 <td ng-class="{'selected-column':determineSelected('assists')}">{{champion.general.assists}}</td> 
 <td ng-class="{'selected-column':determineSelected('largestKillingSpree')}">{{champion.general.largestKillingSpree}}</td> 
 <td ng-class="{'selected-column':determineSelected('totalDamageDealtToChampions')}">{{champion.general.totalDamageDealtToChampions}}</td> 
 <td ng-class="{'selected-column':determineSelected('totalDamageTaken')}">{{champion.general.totalDamageTaken}}</td> 
 <td ng-class="{'selected-column':determineSelected('totalHeal')}">{{champion.general.totalHeal}}</td> 
 <td ng-class="{'selected-column':determineSelected('minionsKilled')}">{{champion.general.minionsKilled}}</td> 
 <td ng-class="{'selected-column':determineSelected('neutralMinionsKilledEnemyJungle')}">{{champion.general.neutralMinionsKilledEnemyJungle}}</td> 
 <td ng-class="{'selected-column':determineSelected('neutralMinionsKilledTeamJungle')}">{{champion.general.neutralMinionsKilledTeamJungle}}</td> 
 <td ng-class="{'selected-column':determineSelected('goldEarned')}">{{champion.general.goldEarned}}</td> 
 <td ng-class="{'selected-column':determineSelected('overallPosition')}">{{champion.general.overallPosition}}</td> 
 <td ng-class="{'selected-column':determineSelected('overallPositionChange')}"><span class="glyphicon" ng-class="{'glyphicon-arrow-up': (champion.general.overallPositionChange > 0), 'glyphicon-arrow-down': (champion.general.overallPositionChange < 0), 'same-position': (champion.general.overallPositionChange === 0)}">{{Math.abs(champion.general.overallPositionChange)}}</span></td> 
</tr>

现在不再显示特定冠军的平均击杀数,而是显示champion.general。在得到的结果中杀死。如何解析页面,使冠军赛。Kills 它会给出一个实际的结果,比如8?

当涉及到从网页中提取数据时,你必须去数据所在的地方。在这种情况下,数据仍然在网页内,这是很好的。您需要获取包含数据的脚本标记并对其进行解析。现在,这个示例代码假定它是索引11处的脚本标记。

public static void main(String[] args)
{
    try
    {
        Document doc = Jsoup
                .connect("http://champion.gg/statistics/")
                .userAgent(
                        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.152 Safari/537.36")
                .get();
        System.out.println(doc.toString());
        Elements table = doc.select("script");
        Element script = table.get(11);
        parseText(script);
    }
    catch (IOException exception)
    {
    }
}
public static void parseText(Element script)
{
    String text = ((DataNode) script.childNode(0)).toString().trim();
    int index = text.indexOf("_id");
    while (index > 0)
    {
        index += 6;// Beginning of value
        int endQuote = text.indexOf("'"", index);
        String id = text.substring(index, endQuote);
        index = text.indexOf("'"key'":'"", endQuote);
        endQuote = text.indexOf("'"", index + 8);
        String key = text.substring(index, endQuote);
        index = text.indexOf("'"kills'":", endQuote);
        endQuote = text.indexOf(",", index);
        String kills = text.substring(index, endQuote);
        text = text.substring(endQuote);
        index = text.indexOf("_id", index);
        System.out.println(id + key + kills);
    }
}
输出:

5812965753 fa9743395ee93a"关键":"Urgot"杀死":

6.47

5812965753 fa9743395ee93b"关键":"Aatrox"杀死":

5.8

5812965753 fa9743395ee93d"关键":"Galio"杀死":

4.58

5812965753 fa9743395ee940"关键":"kl"杀死":7.3div…

我在ProgrammersBlock的帮助下找到了答案。通过检索脚本数据,我把它从JSON变成了一个完整的java对象!

package com.databot.web.parser;
import java.io.IOException;
import java.io.StringReader;
import java.util.ArrayList;
import java.util.List;
import java.util.logging.Level;
import org.jsoup.Jsoup;
import org.jsoup.nodes.DataNode;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import com.databot.Program;
import com.databot.Settings;
import com.databot.champions.ChampionStats;
import com.databot.champions.Champion;
import com.google.gson.stream.JsonReader;
public class WebParser {
public void connect(String url) {
    try {
        Document doc = Jsoup.connect(url).userAgent("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.152 Safari/537.36").get();
        Elements table = doc.select("script");
        Element script = table.get(11);
        parseText(script);
    } catch(IOException exception) {
        if(Settings.DEBUG) {
            Program.LOGGER.log(Level.SEVERE, "There was an error reading the document with the supplied URL!", exception);
        }
        Program.alert("Error loading webpage!");
    }
}
public void parseText(Element script)
{
    String text = ((DataNode) script.childNode(0)).toString().substring(22).trim();
    System.out.println(text);
    List<Champion> champions = new ArrayList<>();
    try {
        JsonReader reader = new JsonReader(new StringReader(text));
        reader.setLenient(true);
        reader.beginArray();
        while(reader.hasNext()) {
            reader.beginObject();
                String id = "", key = "", role = "", title = "";
                ChampionStats stats = new ChampionStats(0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0, 0);
            while(reader.hasNext()) {
                String name = reader.nextName();
                if(name.equalsIgnoreCase("_id")) {
                    id = reader.nextString();
                } else if(name.equalsIgnoreCase("key")) {
                    key = reader.nextString();
                } else if(name.equalsIgnoreCase("role")) {
                    role = reader.nextString();
                } else if(name.equalsIgnoreCase("title")) {
                    title = reader.nextString();
                } else if(name.equalsIgnoreCase("general")) {
                    double winPercent = 0, playPercent = 0, banRate = 0, experience = 0, kills = 0, deaths = 0, assists = 0, totalDamageDealtToChampions = 0, totalDamageTaken = 0, totalHeal = 0, largestKillingSpree = 0, minionsKilled = 0, neutralMinionsKilledTeamJungle = 0, neutralMinionsKilledEnemyJungle = 0, goldEarned = 0; 
                    int overallPosition = 0, overallPositionChange = 0;
                        reader.beginObject();
                        while(reader.hasNext()) {
                            String gName = reader.nextName();
                            if(gName.equalsIgnoreCase("winPercent")) {
                                winPercent = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("playPercent")) {
                                playPercent = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("banRate")) {
                                banRate = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("experience")) {
                                experience = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("kills")) {
                                kills = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("deaths")) {
                                deaths = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("assists")) {
                                assists = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("totalDamageDealtToChampions")) {
                                totalDamageDealtToChampions = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("totalDamageTaken")) {
                                totalDamageTaken = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("totalHeal")) {
                                totalHeal = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("largestKillingSpree")) {
                                largestKillingSpree = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("minionsKilled")) {
                                minionsKilled = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("neutralMinionsKilledTeamJungle")) {
                                neutralMinionsKilledTeamJungle = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("neutralMinionsKilledEnemyJungle")) {
                                neutralMinionsKilledEnemyJungle = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("goldEarned")) {
                                goldEarned = reader.nextDouble();
                            } else if(gName.equalsIgnoreCase("overallPosition")) {
                                overallPosition = reader.nextInt();
                            } else if(gName.equalsIgnoreCase("overallPositionChange")) {
                                overallPositionChange = reader.nextInt();
                            } else {
                                reader.skipValue();
                            }
                        }
                        reader.endObject();
                        stats = new ChampionStats(winPercent, playPercent, banRate, experience, kills, deaths, assists, totalDamageDealtToChampions, totalDamageTaken, totalHeal, largestKillingSpree, minionsKilled, neutralMinionsKilledTeamJungle, neutralMinionsKilledEnemyJungle, goldEarned, overallPosition, overallPositionChange);
                } else {
                    reader.skipValue();
                }
            }
            reader.endObject();
            champions.add(new Champion(id, key, role, title, stats));
        }
        reader.endArray();
        reader.close();
    } catch (Exception e) {
        Program.alert("Error reading JSON data!");
        e.printStackTrace();
    }
    champions.forEach(champion -> {
        System.out.println(champion.toString());
    });
}
}

这是我完整的WebParser类,如果有人感兴趣,我相信有一个更好的方式或更有效的方式来写这个,但这是什么为我工作到现在!